Narrareach

Draft a direct-message reply

create_dm_reply_draft

Save a reply to one of the writer's direct-message conversations for review. Omit text to have Narrareach suggest one in the writer's voice from the recent messages; group chats get no suggestion (dm_reply_group_chat_suggestion_off), so pass the writer's own text there. Nothing is sent: show the writer the full text and ask before calling send_dm_reply_draft. Replaces an unsent draft for the same conversation. replyWindow says whether a reply can go out now: Instagram and Facebook take replies up to 7 days after the reader's last message, TikTok 48 hours, Bluesky and Substack any time. Requires the Revenue Writer plan or above.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "conversationId": "<conversationId>"
    },
    "name": "create_dm_reply_draft"
  }
}

Input Schema

Name	Required	Description	Default
`text`	No	The reply. Omit to get a suggestion in the writer's voice.
`conversationId`	Yes

Output Schema

Name	Required	Description	Default
`draft`	Yes
`replyWindow`	Yes
`connectedAccount`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 11, 2026

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing that nothing is sent, that the agent should show the full text and get confirmation, that an existing unsent draft is overwritten, that a plan tier is required, and that platform-specific reply windows (7 days for Instagram/Facebook, 48 hours for TikTok) gate whether a reply can go out. These are exactly the behavioral constraints an agent needs for a non-read-only mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core action first and packs the safety, plan, and platform-window constraints into compact sentences with no filler. The parenthetical flag reference (dm_reply_group_chat_suggestion_off) and the dense final sentence slightly reduce readability but each clause carries real information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no explanation, and the description covers the remaining agent-critical facts: the tool is a draft-only write, it overwrites prior unsent drafts, plan gating, and platform deadline limits. The only residual gap is sourcing conversationId, which is minor against the overall coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 50%: the text parameter is documented in the schema and reinforced by the description's 'omit to get a suggestion' rule, but conversationId has no description anywhere and the definition never says how to obtain a valid value (e.g., via get_conversation). The definition therefore does not fully compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — save a reply draft into one of the writer's DM conversations — and immediately bounds it against sibling tools by naming send_dm_reply_draft as the separate action. An agent can tell it apart from create_reader_reply_draft and update_dm_reply_draft from the text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit operational conditions: omit text to get a suggested reply, pass the writer's own text for group chats because suggestions are disabled there, and confirm with the writer before invoking send_dm_reply_draft. It omits any mention of update_dm_reply_draft, so the boundary between 'replaces an unsent draft' and the dedicated update tool is left ambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Narrareach tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?